vfio/pds: Fix mutex lock->magic != lock warning

[ Upstream commit 91aeb563bd4332e2988f8c0f64f125c4ecb5bcb3 ]

The following BUG was found when running on a kernel with
CONFIG_DEBUG_MUTEXES=y set:

DEBUG_LOCKS_WARN_ON(lock->magic != lock)
RIP: 0010:mutex_trylock+0x10d/0x120
Call Trace:
 <TASK>
 ? __warn+0x85/0x140
 ? mutex_trylock+0x10d/0x120
 ? report_bug+0xfc/0x1e0
 ? handle_bug+0x3f/0x70
 ? exc_invalid_op+0x17/0x70
 ? asm_exc_invalid_op+0x1a/0x20
 ? mutex_trylock+0x10d/0x120
 ? mutex_trylock+0x10d/0x120
 pds_vfio_reset+0x3a/0x60 [pds_vfio_pci]
 pci_reset_function+0x4b/0x70
 reset_store+0x5b/0xa0
 kernfs_fop_write_iter+0x137/0x1d0
 vfs_write+0x2de/0x410
 ksys_write+0x5d/0xd0
 do_syscall_64+0x3b/0x90
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

As shown, lock->magic != lock. This is because
mutex_init(&pds_vfio->state_mutex) is called in the VFIO open path. So,
if a reset is initiated before the VFIO device is opened the mutex will
have never been initialized. Fix this by calling
mutex_init(&pds_vfio->state_mutex) in the VFIO init path.

Also, don't destroy the mutex on close because the device may
be re-opened, which would cause mutex to be uninitialized. Fix this by
implementing a driver specific vfio_device_ops.release callback that
destroys the mutex before calling vfio_pci_core_release_dev().

Fixes: bb500dbe2ac6 ("vfio/pds: Add VFIO live migration support")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20231122192532.25791-2-brett.creeley@amd.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c
index 649b18e..8c9fb87 100644 (file)
--- a/drivers/vfio/pci/pds/vfio_dev.c
+++ b/drivers/vfio/pci/pds/vfio_dev.c
@@ -155,6 +155,8 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
 
        pds_vfio->vf_id = vf_id;
 
+       mutex_init(&pds_vfio->state_mutex);
+
        vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P;
        vdev->mig_ops = &pds_vfio_lm_ops;
        vdev->log_ops = &pds_vfio_log_ops;
@@ -168,6 +170,16 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
        return 0;
 }
 
+static void pds_vfio_release_device(struct vfio_device *vdev)
+{
+       struct pds_vfio_pci_device *pds_vfio =
+               container_of(vdev, struct pds_vfio_pci_device,
+                            vfio_coredev.vdev);
+
+       mutex_destroy(&pds_vfio->state_mutex);
+       vfio_pci_core_release_dev(vdev);
+}
+
 static int pds_vfio_open_device(struct vfio_device *vdev)
 {
        struct pds_vfio_pci_device *pds_vfio =
@@ -179,7 +191,6 @@ static int pds_vfio_open_device(struct vfio_device *vdev)
        if (err)
                return err;
 
-       mutex_init(&pds_vfio->state_mutex);
        pds_vfio->state = VFIO_DEVICE_STATE_RUNNING;
        pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
 
@@ -199,14 +210,13 @@ static void pds_vfio_close_device(struct vfio_device *vdev)
        pds_vfio_put_save_file(pds_vfio);
        pds_vfio_dirty_disable(pds_vfio, true);
        mutex_unlock(&pds_vfio->state_mutex);
-       mutex_destroy(&pds_vfio->state_mutex);
        vfio_pci_core_close_device(vdev);
 }
 
 static const struct vfio_device_ops pds_vfio_ops = {
        .name = "pds-vfio",
        .init = pds_vfio_init_device,
-       .release = vfio_pci_core_release_dev,
+       .release = pds_vfio_release_device,
        .open_device = pds_vfio_open_device,
        .close_device = pds_vfio_close_device,
        .ioctl = vfio_pci_core_ioctl,